founder-led-content
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFE
Full Analysis
- [REMOTE_CODE_EXECUTION]: No remote code execution or untrusted downloads were detected. The skill relies entirely on local scripts provided within the package.
- [DATA_EXFILTRATION]: No network operations or sensitive file access patterns were found. The tool operates locally and does not attempt to send data to external servers.
- [DYNAMIC_EXECUTION]: The Node.js script uses a static function mapping for its command-line interface, which is a safe practice. It avoids the use of dangerous functions like eval() or exec().
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied business context and post drafts. While this constitutes an ingestion surface, the skill lacks dangerous capabilities (such as network access or file system write permissions) that could be exploited via injection. Furthermore, it includes specific guardrails for verifying content authenticity.
- [CREDENTIALS_UNSAFE]: No hardcoded credentials or unsafe secret management practices were observed.
Audit Metadata